@inproceedings{fernandez-gonzalez-gomez-rodriguez-2018-dynamic,
    title = "Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing",
    author = "Fern{\'a}ndez-Gonz{\'a}lez, Daniel  and
      G{\'o}mez-Rodr{\'i}guez, Carlos",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/D18-1161/",
    doi = "10.18653/v1/D18-1161",
    pages = "1303--1313",
    abstract = "We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manage to notably increase their accuracy, in comparison to that obtained by performing classic static training. In addition, by improving the performance of the state-of-the-art in-order shift-reduce parser, we achieve the best accuracy to date (92.0 F1) obtained by a fully-supervised single-model greedy shift-reduce constituent parser on the WSJ benchmark."
}